© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14177
    Prev
    Next
    INDEX
    Explanations

    variable assignment or list parsing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orgen
    -0.07
    æĪ®
    -0.07
     ugyanis
    -0.07
    bjerg
    -0.07
    ãģ§ãģĻãģ®ãģ§
    -0.06
    umpt
    -0.06
    rowave
    -0.06
    åıĺæĽ´åIJİ
    -0.06
    ml
    -0.06
    mq
    -0.06
    POSITIVE LOGITS
    íĥĿ
    0.08
    ä¸İä¹ĭ
    0.07
    idable
    0.07
    é£ŀå¿«åľ°
    0.07
    ero
    0.07
    åIJĵ
    0.07
    æŀ«
    0.07
    uge
    0.07
    iously
    0.06
    .NaN
    0.06
    Activations Density 0.021%

    No Known Activations